Subarna Shakya

• PhD Computer Engineeing
• Tribhuvan University

This paper presents an end-to-end deep learning model for Automatic Speech Recognition (ASR) that transcribes Nepali speech to text. The model was trained and tested on the OpenSLR (audio, text) dataset. The majority of the audio dataset have silent gaps at both ends which are clipped during dataset preprocessing for a more uniform mapping of audio...

We are delighted to jointly introduce the proceedings of the 4th edition of the European Alliance for Innovation (EAI) International Conference on Smart Governance for Sustainable Smart Cities (SmartGov 2022) and the 3rd edition of the EAI International Conference on Intelligent Edge Processing in the IoT Era (Edge-IoT 2022). These conferences brou...

This book includes high-quality research papers presented at the Fourth International Conference on Image Processing and Capsule Networks (ICIPCN 2023), which is held in Bangkok, Thailand, during 10–11 August 2023. This book provides a collection of the state-of-the-art research attempts to tackle the challenges in image and signal processing from...

In educational institutions, learning analytics and knowledge attainment are the primary concerns, but the students’ academic performance or final results are also very much concerned issues to be addressed. An early prediction of students’ academic performance assists in improving their achievement. The prediction of students’ final examination re...

Sentiment analysis and topic modeling has wide range of applications from medical to entertainment industry, corporates, politics and so on. News media play vital role in shaping the views of public towards any product or people. The dataset used for this work is news headlines dataset of one of the leading new portals of India i.e., Times of India...

The price of a stock in the market can be influenced by many factors, out of which the sentiment of the investors plays a vital role. Most often, the sentiment of investors depends on the sentiment of the news headlines. Therefore, news headlines also play an important role in the fluctuation of the stock index. This paper uses the combination of B...

In Nepali language, compound word formation is mostly associated with inflection, derivation, and postposition attachment. Inflection occurs due to suffixation, whereas derivation is driven by both prefixation and suffixation. The compound word generated by the rules may produce lots of out-of-vocabulary words due to limited lexical resources and n...

Rice cultivation in Nepal is effect by many factors, one of the main factor is rice leaf diseases which limits the crops production. Image classification of rice leaf classify different rice leaf diseases. Image dataset of rice leaf diseases is taken from open source platform. Pre-processing of image is done which is followed by feature extraction...

The excitement about the 5G wireless network has passed. Mobile network operators (MNO) have begun rolling out 5G networks alongside 4G cellular networks in lower frequency and mid-frequency bands (i.e., 3-6 GHz) all over the world. The mid-frequency band can greatly improve the performance of the current network (i.e., 50 MHz–100 MHz). All we know...

p> Intelligent stock trading systems are demand of the modern information age. This research paper proposed a directional movement index based machine learning (DMI-ML) strategy for predicting stock trading signals. Performance of the proposed strategy was evaluated in terms of annual rate of return (ARR), Sharpe ratio (SR), and percentage of profi...

Many types of research are based on students' past data for predicting their performance. A lot of data mining techniques for analyzing the data have been used so far. This research project predicts the higher secondary students' results based on their academic background, family details, and previous examination results using three decision tree a...

This paper presents an end-to-end deep learning model for Automatic Speech Recognition (ASR) that transcribes Nepali speech to text. The model was trained and tested on the OpenSLR (audio, text) dataset. The majority of the audio dataset have silent gaps at both ends which are clipped during dataset preprocessing for a more uniform mapping of audio...

The Internet of Things (IoT) is a paradigm that is rapidly growing in all important fields of telecommunications. Cloud computing is a computing technique that provides a large amount of storage space for data enhancement. The integration of IoT and cloud computing expands storage space for a larger number of users while maintaining the data commun...

In recent years, the concept of automatic colorization of grayscale images has gotten more attention in research for image quality enhancement. The image colorization has a variety of applications such as restoration of historical photographs or deteriorated photographs and the storing of grayscale photographs. The grayscale images represent only t...

In recent years, the application of human facial images has increased significantly for social networks, visual surveillance, biometric analysis, and other commercial use. The applications mainly focus on the age, gender, and ethnicity of persons to build social activities and commercial ads. But the age, gender, and ethnicity prediction are a very...

In recent years, the application of human facial images has increased significantly for social networks, visual surveillance, biometric analysis, and other commercial use. The applications mainly focus on the age, gender, and ethnicity of persons to build social activities and commercial ads. But the age, gender, and ethnicity prediction are a very...

Diabetes is a disease caused due to malfunctioning of pancreas. In this disease, pancreas either no longer produces insulin or produces insufficient insulin. If this disease is diagnosed early, several health complications can be avoided by taking precautions timely. Otherwise, it may create serious health problems. Nowadays, machine learning model...

Personal computer-based data collection and analysis systems may now be more resilient due to the recent advances in digital signal processing technology. The signal processing approach known as Speaker Recognition, uses the specific information contained in voice waves to automatically identify the speaker. For a single source, this study examines...

Chaulagain, DuryodhanPudashine, KumarPaudyal, RajendraMishra, SagarShakya, SubarnaTraditional load balancer has no flexibility to manage growing network traffic in real time and is expensive too. Software-defined networking (SDN) is a promising solution for handling today’s growing network architecture. To address issues such as network congestion...

Health-related applications are one of the most sensitive area which should be delivered on time efficiently. For the storage and processing of enormous health data, Cloud Computing could not be efficient as Cloud Data Centers take large time to process and send back the results. The new paradigm, called Fog Computing is applicable in cases like th...

Remote and dangerous fields that are expensive, complex, and unreachable to reach human insights are examined with ease using the Wireless Sensor Network (WSN) applications. Due to the use of non-renewable sources of energy, challenges with respect to the network lifetime, fault tolerance and energy consumption are faced by the self-managed network...

A building automation system is a centralized intelligent system, which controls the operation of energy, security, water, and safety by the help of hardware and software modules. The general software modules employed for automation process have an algorithm with pre-determined decisions. However, such pre-determined decision algorithms won’t work...

Wastage of electricity occurs in all places starting from a small house electrical loading to a heavy industrial electrical loading. KiloVolt-Ampere Reactive (KVAR) power metering devices are employed in industrial applications for measuring the energy utilization which measure the energy wastage along with it. This urges a consumer to pay for the...

Greenhouses are designed to provide the desired climatic condition for the growth of certain plants to obtain better yield. Most of the greenhouses are developed with adequate windows that allows the natural air to reach the plants to maintain the ideal temperature. The windows are usually operated manually by verifying the greenhouse temperature a...

Stock price forecasting in the field of interest for many stock investors to earn more profit from stock trading. Nowadays, machine learning researchers are also involved in this research field so that fast, accurate and automatic stock price forecasting can be achieved. This research paper evaluated GRU network’s performance with weight decay reg-...

Face recognition at a distance (FRAD) is one of the most difficult types of face recognition applications, particularly at a distance. Due to the poor resolution of facial image, it is difficult to identify faces from a distance. Recently, while recording individuals, the camera view is broad and just a small portion of a person's face is visible i...

Thermal imaging is utilized as a technique in agricultural crop water management due to its efficiency in estimating canopy surface temperature and the ability to predict crop water levels. Thermal imaging was considered as a beneficial integration in Unmanned Aerial Vehicle (UAV) for agricultural and civil engineering purposes with the reduced wei...

Software Defined Networking (SDN) has been a major focus of research works, a solution for handling today's growing network architecture.For handling large number of web requests, network entities like Routers, Switches, Servers, Firewalls, Load Balancers,etc are deployed at different locations of globe by Web Service providers.To address issues su...

By contributing to the system enhancement, the integration of Nano systems for nanosensors with biomaterials proves to be a unique element in the development of novel innovative systems. The techniques by which manipulation, handling, and preparation of the device are accomplished with respect to industrial use are a critical component that must be...

Mishra, SagarJoshi, BasantaPaudyal, RajendraChaulagain, DuryodhanShakya, SubarnaFacial emotion recognition has been an active research topic with its extensive applications in the field of health care, videoconferencing, security and authentication and many more. Human facial emotion recognition (anger, happiness, sadness, etc.) is still a challeng...

Renewable energy sources are gaining a significant research attention due to their economical and sustainable characteristics. In particular, solar power stations are considered as one of the renewable energy systems that may be used in different locations since it requires a lower installation cost and maintenance than conventional systems, despit...

Nowadays stock price prediction is an active area of research among machine learning researchers. One of the main problems with machine learning models is overfitting. Regularization techniques are widely used approaches to avoid over-fitted models. L2 regularization is one of the most popular and widely used regularization techniques. Regularizati...

The ability of wireless sensor networks (WSN) and their functions are degraded or eliminated by means of intrusion. To overcome this issue, this paper presents a combination of machine learning and modified grey wolf optimization (MLGWO) algorithm for developing an improved intrusion detection system (IDS). The best number of wolves are found by ru...

Smart city is a quickly developing approach that is powered by Internet of Things (IoTs), providing a number of services such as collaborative diagnosis and intelligent transportation. In general, in a smart city, the terminals have certain limitations that crib their capability of processing cross application and diversified services. Due to insuf...

Navigation, aviation and several other fields of engineering extensively make use of rotating machinery. The stability and safety of the equipment as well as the personnel are affected by this machinery. Use of deep learning as the basis of intelligent fault diagnosis schemes has and investigation of other relevant fault diagnosis schemes has a lar...

Stock price prediction has been the aim of stock investors since the beginning, which is important for the investors to make rational decisions about buying and selling stocks. Nowadays deep learning techniques and technical indicators are popular tools among researchers for predicting stock prices. Mainly researchers from the field of computer sci...

A multi-cell Fog-Radio Access Network (F-RAN) architecture that takes into consideration the noisy interference from Internet of Things (IoT) devices and transmission takes place in the uplink with grant-free access. An edge node is used to connect the devices present in every cell and will hold a reasonable capacity in the central processor. The r...

This paper proposed a hill-climbing powered gated recurrent unit (HC-GRU) network to predict stock trading signals using the mean average convergence divergence (MACD) indicator. The proposed model was compared with the Buy/Hold Strategy, a benchmark strategy, and the traditional MACD indicator based trading strategy. All three models were evaluate...

Wireless Body Sensor Network (BSNs) are devices that can be worn by human beings. They have sensors with transmission, computation, storage and varying sensing qualities. When there are multiple devices to obtain data from, it is necessary to merge these data to avoid errors from being transmitted, resulting in a high quality fused data. In this pr...

In natural language processing, machine translation is an automated system that analyzes text from a source language (SL), applies some computation on that input, and generates equivalent sentences in the desired destination language (DL) without any human engagement. Recurrent neural network (RNN), a deep learning paradigm has been proved as an ef...

One of the most promising fields of vehicular fog computing (VFC) is by using it as a means to build a parking lot allotment system. Integrating this with parked vehicle assistance system, we can use VFC to its full potential. In this paper, we propose an automatic vehicle allocation system that guides the vehicles on the move to their allotted par...

Information transformed over a long distance without any means like wires, cables and other forms of conductors. The term wireless communication is broad which incorporate different forms of communication and connecting between more devices without any mode of wires through this wireless communication technology. In pre-industrial age, the first ne...

This book includes papers on intelligent expert systems and sustainability applications in the areas of data science, image processing, wireless communication, risk assessment, healthcare, intelligent social network mining, and energy. The recent growth of sustainability leads to a progressively new era of computing, where its design and deployment...

Machine Learning techniques have got a rich focus on agriculture management systems due to its significant improvement in classification algorithms. The agricultural data is difficult to study because they consist of different attributes such as geographic locations, soil types, and seasonal conditions. It is challenging to identify the most import...

Artificial intelligence (AI) plays vital role in disaster management. AI not only can save lives of people during an emergency, it can help government to formulate strategies for increased safety and resiliency before a disaster strikes. In this paper the benefits of AI technologies in disaster response focusing to Nepal have been explored. This pa...

The advancement of virtualization technologies and benefit of economies of implementation cloud data center and proper operation for small and medium-sized enterprises, public and private sectors are seeking implementing and salable IT Solutions such as cloud data centers hosted either in house or by third party. Cloud data center availability, oft...

Software testing is an important process in product development of software companies to ensure the product quality. The developed application must satisfy the customer needs and meets the industrial standards without any compromise. Thus, verification of products through manual test engineer and validate the product once it meets all the necessary...

In the present research era, machine learning is an important and unavoidable zone where it provides better solutions to various domains. In particular deep learning is one of the cost efficient, effective supervised learning model, which can be applied to various complicated issues. Since deep learning has various illustrative features and it does...

https://www.springer.com/gp/book/9783030518585 This book emphasizes the emerging building block of image processing domain, which is known as capsule networks for performing deep image recognition and processing for next-generation imaging science. Recent years have witnessed the continuous development of technologies and methodologies related to...

As the use of Internet-of-Things in day to lives increases, its connection with objects and use of sensors has increased in number largely. These objects are also integrated with the internet, enabling its application in many more complex systems. Though efforts have been implemented to protect the security management, there are some major challeng...

In the modern world, software plays an integral role, following an effective methodology while developing these software have become crucial to accomplish the project goal. Agile approach is a methodology which have been introduced as an effective approach for developing software to increase productivity and efficacy of software development process...

Sign Language is the method of communication of deaf and dumb people all over the world. However, it has always been a difficulty in communication between a verbal impaired person and a normal person. Sign Language Recognition is a breakthrough for helping deaf-mute people to communicate with others. The commercialization of an economical and accur...

We present a new approach to video compression for video surveillance by refining the shortcomings of conventional approach and substitute each traditional component with their neural network counterpart. Our proposed work consists of motion estimation, compression and compensation and residue compression, learned end-to-end to minimize the rate-di...

The diverse user demands in the system supported with the internet of things are often managed efficiently, using the computing system that is pervasive. Pervasive computing system in an integration of heterogeneous distributed network and communication technologies and other referred as the ubiquitous computing. All though it handles the user requ...

Most of the existing software systems are web-based and interactive. Semantic Web Technologies further allows for organizing and encoding information meaningfully. It enables software agents to interpret the information. However, the representation of information in different format has made challenging to interoperate among the heterogeneous syste...

There has been increasing demand of security and safety in public as well as private places and hence surveillance system using IoT sensors, cameras has become the most important part in our daily life. This system has to operate all times 24/7/365 and thus produces huge amounts of data. Cloud computing offers storage, processing, and analytical se...

This paper proposes a fuzzy PI speed controller which is used in electric vehicle’s drive control system insensitive to parameter change and disturbance, using fuzzy control theory. A permanent magnet synchronous motor (PMSM) is modelled mathematically in d-q reference frame. In this paper, a sliding model and fuzzy control theory are used to simul...

The adhoc networks are the platforms formed for specific reason to attain a specific purpose. It is a communication strategy followed by the wireless devices when or while the actual communication setup is not possible. Any portable device communicating in the wireless medium in a decentralized manner is termed to be a wireless adhoc network. One s...

A nondeterministic polynomial (NP) with complete Multicast routing problem is defined using a bi-velocity particle swarm optimization (BVDPSO) is proposed in this paper. The shift of particle swarm optimization to the discrete or binary domain, stepping away from the continuous domain is the major impact of the work. Initially a bi-velocity strateg...

Time is an essential resource for everyone wants to save in their life. The development of technology inventions made this possible up to certain limit. Due to life style changes people are purchasing most of their needs on a single shop called super market. As the purchasing item numbers are huge, it consumes lot of time for billing process. The e...

A novel platform of dispersed streaming is developed by the fog paradigm for the applications associated with the internet of things. The sensed information’s of the IOT plat form is collected from the edge device closer to the user from the lower plane and moved to the fog in the middle of the cloud and edge and then further pushed to the cloud at...

The advanced improvements in the techniques utilized in the field of energy generation using the wind mills has led to the remarkable minimization in its capital investments and the cost incurred in its operation. This has even enhanced the prominence of the winds farms worldwide and has raised the market share of the energy produced using the wind...

The advancement and development of proficient technologies that exploit sensors and things connected with the internet respectively along with the progress of the associated protocols has greatly encouraged the growth of applications that are basically dependent on the sensors for observing the happenings. Multitudes of such applications have been...

The emergence of the cloud computing, and the other advanced technologies has made possible the extension of the computing and the data distribution competencies of the robotics that are networked by developing an cloud based robotic architecture by utilizing both the centralized and decentralized cloud that is manages the machine to cloud and the...

Energy is an essential parameter for any work to be done. An electric energy is a primary requirement for any wireless transmission system. Transmitting the information from a source to destination requires a continuous and strengthen wireless network connection to avoid interruption from electromagnetic disturbance. Powering such wireless networks...

A WANET is a specific type of Adhoc network with a community of specialized, self-organizing mobile devices. Because of the complex existence of mobile devices and wireless networking, the adhoc network communicating in wireless manner faces many problems related to the topological organizations , battery capacity limitations that results in energy...

With a view to overcome the shortcomings of traditional Electronic Health Record (EHR) system so as to assure the interoperability by providing open access to sensitive health data, while still preserving personal data privacy, anonymity and avoiding data misuse, Decentralized Electronic Health Record System was developed. The aforementioned issue...

E-government uses information and communication technologies (ICTs) tools and systems to provide better public services. Database Management System (DBMS) is a very significant part in e-governance activities and process in the nation. Security of the data is a main concern of the organizations and private. Proper database management and data secur...

Abstract— A handwritten signature commonly practiced route for confirming the authenticity of legal documents. The verification of the signature is critical as it varies every time and may change with age, behavior, and environment. This paper presents a Deep learning model based on the CNN architecture to verify the signature. For experimental pur...

This book focuses on the emerging advances in distributed communication systems, big data, intelligent computing and Internet of Things, presenting state-of-the-art research in frameworks, algorithms, methodologies, techniques and applications associated with data engineering and wireless distributed communication technologies. In addition, it disc...

Stock market prediction is an attempt of determining the future value of a stock traded on a stock exchange. Stock market investors try to predict the stock’s future price to make trading decisions such that optimum profit can be earned. Deep learning models are found most successful in predicting stock prices. This paper has performed a novel anal...

The stock price is the cost of purchasing a security or stock in a stock exchange. The stock price prediction has been the aim of investors since the beginning of the stock market. It is the act of forecasting the future price of a company's stock. Nowadays, deep learning techniques are widely used for identifying the stock trends from large amount...

The technological growth in our day to day life and its integration advancements in the communication network to activate a seamless communication have led to digital transformation in almost all applications. This causes a huge set of digital information conveyance via email, audio and video calls connecting people at all times. These data that ar...

Over the past decade, rapid progress in ICT has encouraged governments to incorporate new technology into their national development strategies. With the growing demands of citizens and changing global rules and regulations, governments are under pressure to deliver quality services at right time. E-government has recently emerged in Nepal that‟s w...

The block chain has become one of the predominant term in the applications like financial, automobile, health care, risk management, and internet of things due to its reliability and more beneficial services. It executes every transaction by establishing trust in the open environment. The deployment of the block chain technology in the various appl...

Measuring effectiveness analysis of civil service is not so easy a job as we think. Information and Communication Technology (ICT) is being a fundamental tool of human beings which is making our daily life activities easy, smart and simplify. ICT has played the role of the pool between civil service and day to day service delivery. In this study, t...

The paper puts forward the methodologies for the virtual restoration of the archeological artifacts that were obtained from the various missions. The proposed methodology combines the both the augmented and the virtual reality (C-ARVR) technologies enabling a virtual restoration of the artifacts that were damaged by visualizing the virtual three di...

The inclusion of semantic information in any similarity measures improves the efficiency of the similarity measure and provides human interpretable results for further analysis. The similarity calculation method that focuses on features related to the text's words only, will give less accurate results. This paper presents three different methods th...

The inclusion of semantic information in any similarity measures improves the efficiency of the similarity measure and provides human interpretable result. This paper presents three different methods to compute semantic similarities between short news texts. These methods are based on corpus-based and knowledge-based methods: cosine similarity usin...

Dermatological diseases rate has been increasing for past few decades. Most of these diseases tend to pass on from one person to another and are also based on visual perspectives, the dermatological diseases of one kind found on one part of the body might look different on another part of the body and diseases of different kinds on one part might l...

Cloud computing is advantageous in several applications. Data migration is constantly carried out to hybrid or public cloud. Certain large enterprises will not move their business-critical data and applications to the cloud. This is due to the concerns regarding data security and privacy protection. In this paper, we provide a data security analysi...

The disorders identified with retina of the eye such as: Diabetic Retinopathy (DR), age-related Macular Degeneration (AMD), Glaucoma, etc. can cause visual impairments. The retinal fundus pictures of the patients can be acquired with a computerized fundus camera. It can then be used as machine learning application against the manual technique for t...

A distributed multimedia system (DMS) come to play as a backbone of 21th century to provide sophisticated technology to realize such a modern distance education/learning. In this paper, we describe distributed multimedia system for distance education that could be implemented at Kathmandu University and how this system interacts with other Universi...

To improve service delivery of government, paper based vital event registration (VER) system should gradually be replaced by ICT based system. This paper highlights the barriers that may stand in implementing ICT in VER. Questionnaire was used to collect primary data. Population size for the research was 6,743 out of which 272 valid responses were...

The increasing popularity of smart phones has led to the dramatic growth in mobile malware especially in Android platform. Many aspects of android permission has been studied for malware detection but sufficient attention has not been given to intent. This research work proposes using Latent Semantic Indexing for malware detection and classificatio...